Determining the face of wearing a mask from not wearing a mask from visual data such as video and still, images have been a fascinating research topic in recent decades due to the spread of the Corona pandemic, which has changed the features of the entire world and forced people to wear a mask as a way to prevent the pandemic that has calmed the entire world, and it has played an important role. Intelligent development based on artificial intelligence and computers has a very important role in the issue of safety from the pandemic, as the Topic of face recognition and identifying people who wear the mask or not in the introduction and deep education was the most prominent in this topic. Using deep learning techniques and the YOLO (”You only look once”) neural network algorithm, which is an efficient real-time object identification algorithm, an intelligent system was developed in this thesis to distinguish which faces are wearing a mask and who is not wearing a wrong mask. The proposed system was developed based on data preparation, preprocessing, and adding a multi-layer neural network, followed by extracting the detection algorithm to improve the accuracy of the system. Two global data sets were used to train and test the proposed system and worked on it in three models, where the first contains the AIZOO data set, the second contains the MoLa RGB CovSurv data set, and the third model contains a combined data set for the two in order to provide cases that are difficult to identify and the accuracy results that were obtained. obtained from the merging datasets showed that the face mask (0.953) and the face recognition system were the most accurate in detecting them (0.916).
Vol. 6, Issue 1 (2025)
Deep learning convolution neural network has been widely used to recognize or classify voice. Various techniques have been used together with convolution neural network to prepare voice data before the training process in developing the classification model. However, not all model can produce good classification accuracy as there are many types of voice or speech. Classification of Arabic alphabet pronunciation is a one of the types of voice and accurate pronunciation is required in the learning of the Qur’an reading. Thus, the technique to process the pronunciation and training of the processed data requires specific approach. To overcome this issue, a method based on padding and deep learning convolution neural network is proposed to
... Show More
(15)
(1)
استهدف البحث تشخيص وتحليل الاسباب التي تجعل المرأة العراقية أكثر تأثراً من الرجل بعوامل التغيرات المناخية، فضلاً عن زيادة الوعي بقضية المرأة في هذا المجال، لأن موضوع دمجها في صياغة السياسات والاستراتيجيات المتعلقة بالتغير المناخي أصبح قضية عالمية، ويحتل مرتبة متقدمة في مؤشرات تحقيق أهداف التنمية المستدامة، وأستخدمت الباحثة المنهج الوصفي والتحليلي والاحصائي في تحليل محاور البحث، وتوصل البحث الى إستن
... Show More
In light of the development in computer science and modern technologies, the impersonation crime rate has increased. Consequently, face recognition technology and biometric systems have been employed for security purposes in a variety of applications including human-computer interaction, surveillance systems, etc. Building an advanced sophisticated model to tackle impersonation-related crimes is essential. This study proposes classification Machine Learning (ML) and Deep Learning (DL) models, utilizing Viola-Jones, Linear Discriminant Analysis (LDA), Mutual Information (MI), and Analysis of Variance (ANOVA) techniques. The two proposed facial classification systems are J48 with LDA feature extraction method as input, and a one-dimen
... Show More
(6)
(2)
Steganography is a useful technique that helps in securing data in communication using different data carriers like audio, video, image and text. The most popular type of steganography is image steganography. It mostly uses least significant bit (LSB) technique to hide the data but the probability of detecting the hidden data using this technique is high. RGB is a color model which uses LSB to hide the data in three color channels, where each pixel is represented by three bytes to indicate the intensity of red, green and blue in that pixel. In this paper, steganography based RGB image is proposed which depends on genetic algorithm (GA). GA is used to generate random key that represents the best ordering of secret (image/text) blocks to b
... Show MoreSteganography is an important class of security which is widely used in computer and network security nowadays. In this research, a new proposed algorithm was introduced with a new concept of dealing with steganography as an algorithmic secret key technique similar to stream cipher cryptographic system. The proposed algorithm is a secret key system suggested to be used in communications for messages transmission steganography
Science, technology and many other fields are use clustering algorithm widely for many applications, this paper presents a new hybrid algorithm called KDBSCAN that work on improving k-mean algorithm and solve two of its
problems, the first problem is number of cluster, when it`s must be entered by user, this problem solved by using DBSCAN algorithm for estimating number of cluster, and the second problem is randomly initial centroid problem that has been dealt with by choosing the centroid in steady method and removing randomly choosing for a better results, this work used DUC 2002 dataset to obtain the results of KDBSCAN algorithm, it`s work in many application fields such as electronics libraries,
Fusidic acid (FA) is a well-known pharmaceutical antibiotic used to treat dermal infections. This experiment aimed for developing a standardized HPLC protocol to determine the accurate concentration of fusidic acid in both non-ionic and cationic nano-emulsion based gels. For this purpose, a simple, precise, accurate approach was developed. A column with reversed-phase C18 (250 mm x 4.6 mm ID x 5 m) was utilized for the separation process. The main constituents of the HPLC mobile phase were composed of water: acetonitrile (1: 4); adjusted at pH 3.3. The flow rate was 1.0 mL/minute. The optimized wavelength was selected at 235 nm. This approach achieved strong linearity for alcoholic solutions of FA when loaded at a serial concentrati
... Show More
(2)
(1)